© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 43318
    Prev
    Next
    INDEX
    Explanations

    importance

    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
    莫
    -0.07
     Armor
    -0.07
    .From
    -0.07
     Inc
    -0.07
     spending
    -0.07
     IMO
    -0.07
     consumes
    -0.07
     Winner
    -0.06
     stuck
    -0.06
    response
    -0.06
    POSITIVE LOGITS
     wład
    0.08
    <|im_end|>
    0.08
    ประโยชน
    0.08
    郅
    0.07
    -placeholder
    0.07
     Investig
    0.07
    observable
    0.07
    깍
    0.07
     LinearGradient
    0.07
    �
    0.07
    Activations Density 0.156%

    No Known Activations