© 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. 39925
    Prev
    Next
    INDEX
    Explanations

    1

    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
    "})↵
    -0.07
     incap
    -0.07
    Container
    -0.07
    倌
    -0.07
    creates
    -0.06
    '})↵
    -0.06
     gone
    -0.06
    نان
    -0.06
     sổ
    -0.06
    뀩
    -0.06
    POSITIVE LOGITS
     incremented
    0.08
    awei
    0.07
    ENDED
    0.07
    ////////////////////////////////////////////////////////////////////////////////
    0.07
    额外
    0.07
    imensional
    0.07
     две
    0.07
     Interrupt
    0.07
    荡
    0.06
     BigDecimal
    0.06
    Activations Density 0.003%

    No Known Activations