© 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. 42388
    Prev
    Next
    INDEX
    Explanations

    boost

    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
    _processing
    -0.08
    delete
    -0.07
     tc
    -0.07
    فل
    -0.07
    icolor
    -0.06
     efect
    -0.06
     Cyber
    -0.06
    	int
    -0.06
    binations
    -0.06
     en
    -0.06
    POSITIVE LOGITS
     zoning
    0.07
    OSH
    0.07
    mak
    0.07
    وافق
    0.07
     fout
    0.07
    맡
    0.07
    recated
    0.07
     כיום
    0.07
     novelty
    0.07
    ме
    0.06
    Activations Density 0.002%

    No Known Activations