Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 59688
    Prev
    Next
    INDEX
    Explanations

    Tech and trivia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -three
    -0.08
    חמ
    -0.07
    thumb
    -0.07
    zp
    -0.07
     الجانب
    -0.07
    śnie
    -0.07
    pired
    -0.07
     görd
    -0.07
    ๆ
    -0.07
    _dm
    -0.07
    POSITIVE LOGITS
     Bans
    0.08
     Gaga
    0.07
     Cant
    0.07
     ACCEPT
    0.07
    游艇
    0.07
    推送
    0.07
     Rece
    0.06
    万博
    0.06
    asier
    0.06
    ଓ
    0.06
    Activations Density 0.000%

    No Known Activations