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. 23-RESID-POST-AA
    6. 130803
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _gene
    -0.07
    taking
    -0.07
     roku
    -0.07
    ën
    -0.07
    不允许
    -0.07
     kleine
    -0.07
    串
    -0.07
    .EN
    -0.06
     Glück
    -0.06
    朔
    -0.06
    POSITIVE LOGITS
    ڨ
    0.08
     ].
    0.07
    خطط
    0.07
    /value
    0.07
    .Format
    0.07
     destroy
    0.07
    aved
    0.06
     redirectTo
    0.06
    踌
    0.06
     writings
    0.06
    Activations Density 0.021%

    No Known Activations