© 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. 15-RESID-POST-AA
    6. 1933
    Prev
    Next
    INDEX
    Explanations

    Time periods (days)

    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
     society
    -0.08
    haps
    -0.08
    旦
    -0.08
    殊
    -0.07
    我不知道
    -0.07
    ecs
    -0.07
    ắc
    -0.07
    tern
    -0.07
     ever
    -0.07
    ima
    -0.07
    POSITIVE LOGITS
     contrace
    0.07
    _locs
    0.06
    𝕁
    0.06
    .metroLabel
    0.06
     WATCH
    0.06
     entreg
    0.06
    겋
    0.06
     Ber
    0.06
    얽
    0.06
    טע
    0.06
    Activations Density 0.012%

    No Known Activations