INDEX

Explanations

I

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

pez

-0.28

_NAV

-0.26

SID

-0.25

SID

-0.25

mania

-0.25

ä»½

-0.24

_SID

-0.24

avy

-0.24

 floated

-0.24

é¡¶

-0.23

POSITIVE LOGITS

antium

0.27

æľ¬ç½ĳ

0.26

ÑİÑīÐ¸Ð¼

0.26

 deciding

0.26

 offend

0.25

 lurking

0.25

 incest

0.25

fÃ¼hrer

0.24

asting

0.24

 Obtain

0.24

Activations Density 0.036%

I

No Comments

No Known Activations