© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 498
    Prev
    Next
    INDEX
    Explanations

    water and swimming

    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
    ‎
    -0.07
    outcome
    -0.07
    циальн
    -0.07
     Straight
    -0.06
    莼
    -0.06
    古老
    -0.06
    IVED
    -0.06
    琇
    -0.06
     shy
    -0.06
    alach
    -0.06
    POSITIVE LOGITS
    -temp
    0.07
    运营
    0.07
    ropsych
    0.07
    *@
    0.07
    꾐
    0.07
     testified
    0.07
    -outline
    0.07
    egend
    0.06
    Validators
    0.06
     режим
    0.06
    Activations Density 0.127%

    No Known Activations