INDEX

Explanations

want to

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

ç®¡çĲĨåĬŀæ³ķ

-0.30

å·¥ä½ľèĢħ

-0.27

TP

-0.27

Å¥

-0.25

 Affairs

-0.24

_weak

-0.24

 related

-0.24

æ¡£

-0.24

è¿Ļéĥ¨åĪĨ

-0.24

é¸¦

-0.24

POSITIVE LOGITS

è¶Ĭå¥½

0.26

getStore

0.25

dere

0.25

 attributeName

0.25

 blink

0.25

 Likewise

0.25

 accum

0.24

 Korean

0.24

Program

0.24

iative

0.24

Activations Density 0.018%

want to

No Comments

No Known Activations