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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 42530
    Prev
    Next
    INDEX
    Explanations

    homeless

    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
     Andersen
    -0.08
    startTime
    -0.07
    ifo
    -0.07
    rek
    -0.07
    .find
    -0.07
    lek
    -0.07
    strt
    -0.07
    ildo
    -0.07
     Slow
    -0.07
    lyphicon
    -0.07
    POSITIVE LOGITS
     canal
    0.07
     rav
    0.07
     scattered
    0.06
    图画
    0.06
    医治
    0.06
    (config
    0.06
    驱
    0.06
     coh
    0.06
    例
    0.06
     Canon
    0.06
    Activations Density 0.261%

    No Known Activations