© 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. 11-RESID-POST-AA
    6. 24900
    Prev
    Next
    INDEX
    Explanations

    ph

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    胫
    -0.07
    śmie
    -0.07
     rendre
    -0.07
    nesday
    -0.07
    📉
    -0.07
    崭
    -0.07
     Trend
    -0.07
    Take
    -0.07
    toJson
    -0.07
    𝑓
    -0.07
    POSITIVE LOGITS
     objects
    0.07
    bubble
    0.07
     vực
    0.07
    Bubble
    0.07
    resas
    0.06
     PST
    0.06
     ông
    0.06
    ые
    0.06
    �
    0.06
    _business
    0.06
    Activations Density 0.002%

    No Known Activations