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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2470
    Prev
    Next
    INDEX
    Explanations

    x

    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
    uxt
    -0.08
    iente
    -0.08
    舔
    -0.07
    yne
    -0.07
     Herz
    -0.07
     Integral
    -0.07
    iete
    -0.07
     Ashe
    -0.07
     Pere
    -0.06
    .insert
    -0.06
    POSITIVE LOGITS
    下來
    0.08
    财报
    0.07
    ↳
    0.07
    覚え
    0.07
    Alarm
    0.07
    otherwise
    0.06
     prep
    0.06
     `$
    0.06
     yerleş
    0.06
    (prom
    0.06
    Activations Density 0.005%

    No Known Activations