INDEX

Explanations

uncertainty or code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

zym

-0.25

å½ĵäºĭ

-0.24

æ¬¾

-0.24

ãģĤãģĴ

-0.24

 Witness

-0.24

æĬļæĳ¸

-0.23

IQ

-0.23

Cat

-0.23

çľĭæľĽ

-0.23

starts

-0.23

POSITIVE LOGITS

exp

0.29

agger

0.28

exp

0.25

ainen

0.24

-bel

0.24

-serving

0.23

.axis

0.23

hotmail

0.23

aran

0.23

PA

0.23

Activations Density 0.005%

uncertainty or code

No Comments

No Known Activations