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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24484
    Prev
    Next
    INDEX
    Explanations

    -gen

    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
     stringByAppendingString
    -0.06
    (Table
    -0.06
    윁
    -0.06
    median
    -0.06
    ᚾ
    -0.06
    and
    -0.06
    دينة
    -0.06
     practically
    -0.06
     ks
    -0.06
    ⁼
    -0.06
    POSITIVE LOGITS
     wage
    0.09
     leases
    0.08
    .roles
    0.07
    ilies
    0.07
    кой
    0.07
    做工
    0.07
    \Blueprint
    0.07
    酱油
    0.07
     wenn
    0.07
     Roose
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.