© 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. 15-RESID-POST-AA
    11. 80579
    Prev
    Next
    INDEX
    Explanations

    unique and across

    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
    Negative Logits
     spare
    -0.07
     getNode
    -0.07
    ropy
    -0.07
     значение
    -0.07
     pneumonia
    -0.07
     prefetch
    -0.07
    _xor
    -0.06
     voltage
    -0.06
    توفر
    -0.06
    (FALSE
    -0.06
    POSITIVE LOGITS
    המל
    0.07
    istes
    0.07
     Facing
    0.07
    ativas
    0.07
    atives
    0.07
                                ↵
    0.07
    acles
    0.07
    /validation
    0.07
    עשי
    0.07
    イス
    0.07
    Activations Density 0.038%

    No Known Activations