© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 57184
    Prev
    Next
    INDEX
    Explanations

    Code/email-related strings

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maker
    -0.08
     aimed
    -0.07
    abl
    -0.07
     Labs
    -0.07
    dn
    -0.07
    Online
    -0.07
     Harris
    -0.07
    online
    -0.07
    ꇗ
    -0.07
     tapi
    -0.07
    POSITIVE LOGITS
     $_[
    0.07
     decorations
    0.07
    (sf
    0.07
    <Self
    0.07
    觯
    0.07
     참
    0.07
     precaution
    0.07
     처리
    0.06
    <num
    0.06
    萩
    0.06
    Activations Density 0.119%

    No Known Activations