© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41193
    Prev
    Next
    INDEX
    Explanations

    H2O2

    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
     Autof
    -0.07
     Especially
    -0.07
    	wc
    -0.07
    /max
    -0.07
    venting
    -0.06
     segreg
    -0.06
     Eins
    -0.06
    OLON
    -0.06
     Hungary
    -0.06
     vacancies
    -0.06
    POSITIVE LOGITS
    ::-
    0.07
    sudo
    0.07
    〷
    0.06
    ירו
    0.06
    SAN
    0.06
    湜
    0.06
    .RESULT
    0.06
    劳务
    0.06
    农民
    0.06
    天上
    0.06
    Activations Density 3.251%

    No Known Activations