© 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 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. 15-RESID-POST-AA
    11. 51473
    Prev
    Next
    INDEX
    Explanations

    References

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spilled
    -0.08
     получа
    -0.07
    TextBoxColumn
    -0.07
     foyer
    -0.07
    ことができます
    -0.07
     phóng
    -0.07
    Malloc
    -0.07
     dòng
    -0.07
    aintenance
    -0.07
    .cmb
    -0.07
    POSITIVE LOGITS
     urges
    0.07
    裎
    0.07
    ücken
    0.07
    Here
    0.07
    ursive
    0.07
     Alarm
    0.07
    inke
    0.07
    ⼋
    0.06
    หม
    0.06
    ErrMsg
    0.06
    Activations Density 0.001%

    No Known Activations