© 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. 50725
    Prev
    Next
    INDEX
    Explanations

    synonym

    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
    assist
    -0.07
     sentencing
    -0.07
     bä
    -0.07
    联赛
    -0.07
     Gst
    -0.07
     $("#"
    -0.07
    十足
    -0.07
     дополн
    -0.07
     Width
    -0.07
     intervention
    -0.07
    POSITIVE LOGITS
    .ManyToMany
    0.07
    הוצ
    0.07
    ᅯ
    0.06
    تسوي
    0.06
    onyms
    0.06
    opacity
    0.06
     synonym
    0.06
     LOW
    0.06
    Happy
    0.06
     synonyms
    0.06
    Activations Density 0.004%

    No Known Activations