INDEX

Explanations

George Washington/Bush

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 excer

-0.31

edin

-0.29

è¯´åĩºæĿ¥

-0.27

ÑĥÐµÑĤÑģÑı

-0.25

æĭĹ

-0.25

 statically

-0.24

orney

-0.24

ä¸¤çº§

-0.24

Ð¸Ð´Ðµ

-0.23

åĿ³

-0.23

POSITIVE LOGITS

sig

0.29

ikit

0.28

sig

0.27

stant

0.26

 Lotto

0.25

åı¯çŁ¥

0.25

æĸ°çļĦ

0.25

oni

0.24

ä¸¾

0.24

Pip

0.24

Activations Density 0.002%

George Washington/Bush

No Comments

No Known Activations