© 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. 542
    Prev
    Next
    INDEX
    Explanations

    delivering legal opinions

    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
    =True
    -0.07
    较强
    -0.07
    𐭓
    -0.07
    ynchronously
    -0.07
    /go
    -0.07
    对其真实
    -0.06
     najbliż
    -0.06
    *self
    -0.06
     PartialEq
    -0.06
    ="#"
    -0.06
    POSITIVE LOGITS
    סר
    0.08
    パタ
    0.08
     sanitized
    0.08
     RTS
    0.07
    AMI
    0.07
    .hs
    0.07
    嬷
    0.07
    申诉
    0.07
     Launcher
    0.07
    VN
    0.07
    Activations Density 0.003%

    No Known Activations