Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 433
    Prev
    Next
    INDEX
    Explanations

    style tag

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acute
    -0.07
    _REFRESH
    -0.07
    RowCount
    -0.07
     Crist
    -0.07
    _cache
    -0.06
    _Options
    -0.06
    וכים
    -0.06
     all
    -0.06
     cls
    -0.06
     cry
    -0.06
    POSITIVE LOGITS
    医治
    0.07
    itle
    0.07
    ᔅ
    0.07
     khiển
    0.07
     Justice
    0.07
    angered
    0.07
     UNESCO
    0.07
    Marvel
    0.06
     Mixer
    0.06
     weap
    0.06
    Activations Density 0.002%

    No Known Activations