INDEX

Explanations

methods

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

å¾Īæ¸ħæ¥ļ

-0.33

AVING

-0.29

 Superintendent

-0.27

æ¸ħæ¥ļ

-0.27

 PROVIDED

-0.27

å§Ķç»Ħç»ĩéĥ¨

-0.27

æĬĵ

-0.26

 dotted

-0.26

idia

-0.26

åĲĮå¿Ĺä»¬

-0.25

POSITIVE LOGITS

sem

0.36

quant

0.34

 simulation

0.32

 quantitative

0.32

kin

0.32

æ¨¡æĭŁ

0.31

 morph

0.31

 quant

0.31

 bootstrap

0.31

 Bayesian

0.31

Activations Density 0.117%

methods

No Comments

No Known Activations