© 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. 19-RESID-POST-AA
    11. 102877
    Prev
    Next
    INDEX
    Explanations

    ]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ade
    -0.07
     codec
    -0.07
    ware
    -0.07
     Derived
    -0.07
    还没有
    -0.07
    ellidos
    -0.06
     эта
    -0.06
    (ld
    -0.06
    -read
    -0.06
    Ē
    -0.06
    POSITIVE LOGITS
     *)__
    0.07
     fossil
    0.07
    .VISIBLE
    0.07
     ча
    0.07
     rencont
    0.07
    記
    0.06
    REA
    0.06
    }\.[
    0.06
     jouer
    0.06
    ",$
    0.06
    Activations Density 0.005%

    No Known Activations