© 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. 129259
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    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
     Whip
    -0.07
     Huss
    -0.07
     Kum
    -0.07
     WV
    -0.07
     Urdu
    -0.07
     spontaneously
    -0.06
    hound
    -0.06
     pioneered
    -0.06
    Labour
    -0.06
     Adv
    -0.06
    POSITIVE LOGITS
    bitrary
    0.07
     completely
    0.07
    ocup
    0.07
    elo
    0.07
    _legacy
    0.07
    板
    0.07
    زواج
    0.07
    entric
    0.06
    折叠
    0.06
    تج
    0.06
    Activations Density 0.018%

    No Known Activations