© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7-RESID-POST-AA
    11. 59888
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    Negative Logits
     certificates
    -0.07
     celebrity
    -0.07
    证券
    -0.07
    _dim
    -0.07
    drivers
    -0.07
    睹
    -0.06
    ♎
    -0.06
     pz
    -0.06
    /trunk
    -0.06
     issuance
    -0.06
    POSITIVE LOGITS
    本次
    0.07
    requestData
    0.07
    琰
    0.07
    ackBar
    0.07
    brick
    0.07
    访
    0.07
    SENSOR
    0.07
     причин
    0.07
     reunited
    0.07
    ませ
    0.07
    Activations Density 0.101%

    No Known Activations