© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 8617
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
     candidate
    -0.07
    可能です
    -0.07
     Kut
    -0.07
     Pitt
    -0.07
     punches
    -0.07
     punch
    -0.07
    绿水青山
    -0.07
     abst
    -0.07
     Wel
    -0.07
    教练
    -0.07
    POSITIVE LOGITS
    올
    0.08
    .Header
    0.08
    违法
    0.07
    个人
    0.07
    (TEXT
    0.07
    DUCT
    0.07
    文档
    0.07
    (lower
    0.07
    _LOCK
    0.07
    小說
    0.07
    Activations Density 0.111%

    No Known Activations