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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2118
    Prev
    Next
    INDEX
    Explanations

    have

    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
    Not in Any Lists

    No Comments

    Negative Logits
    /git
    -0.07
    descr
    -0.07
    .setAuto
    -0.07
     Start
    -0.07
    Handles
    -0.07
     mitochondrial
    -0.07
    这个地图
    -0.07
    culo
    -0.06
    _mail
    -0.06
    Redux
    -0.06
    POSITIVE LOGITS
    เอส
    0.07
    高尔夫
    0.07
     pauses
    0.07
     seller
    0.07
    .SelectedIndexChanged
    0.07
    起码
    0.07
     ponds
    0.06
    marshall
    0.06
    拦
    0.06
     tether
    0.06
    Activations Density 0.024%

    No Known Activations