© 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. 23-RESID-POST-AA
    6. 703
    Prev
    Next
    INDEX
    Explanations

    Government and organizations

    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
     где
    -0.07
     https
    -0.07
     json
    -0.06
    lung
    -0.06
     carcin
    -0.06
     ISIS
    -0.06
    /trunk
    -0.06
     link
    -0.06
    fdb
    -0.06
    .nil
    -0.06
    POSITIVE LOGITS
    嗥
    0.07
    Copying
    0.07
    𝒂
    0.07
    expiry
    0.07
    蕙
    0.07
    𝒎
    0.07
    .(*
    0.06
    _EVENTS
    0.06
    못
    0.06
    �
    0.06
    Activations Density 0.058%

    No Known Activations