© 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. 6310
    Prev
    Next
    INDEX
    Explanations

    Number patterns

    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
     Fitzgerald
    -0.07
    olec
    -0.07
    .GetName
    -0.07
    𝚈
    -0.07
    alion
    -0.06
    垤
    -0.06
     nevertheless
    -0.06
     Конечно
    -0.06
     téc
    -0.06
    整个人
    -0.06
    POSITIVE LOGITS
    Pe
    0.07
    ()][
    0.07
     flavors
    0.06
    Cast
    0.06
    material
    0.06
    IAM
    0.06
    .Sh
    0.06
    点了
    0.06
    .vo
    0.06
    Disabled
    0.06
    Activations Density 0.014%

    No Known Activations