© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 76332
    Prev
    Next
    INDEX
    Explanations

    nouns referring to people that use the -man/-men suffix, including plural and possessive forms.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ("@
    -0.08
     ()=>
    -0.07
     HttpServletResponse
    -0.07
     Bon
    -0.07
    遇见
    -0.07
     Bind
    -0.07
    .pub
    -0.07
    /j
    -0.07
     adolescent
    -0.07
     incorporation
    -0.07
    POSITIVE LOGITS
    Scaler
    0.08
     scor
    0.07
    men
    0.07
     salesman
    0.07
     lapse
    0.07
     MPU
    0.07
    SEM
    0.07
    ">#
    0.07
    usband
    0.06
    klä
    0.06
    Activations Density 0.017%

    No Known Activations