INDEX

Explanations

at

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

erva

-0.28

ecast

-0.27

ections

-0.27

èįļ

-0.27

quire

-0.25

space

-0.25

é¡º

-0.25

cente

-0.25

outines

-0.24

holds

-0.24

POSITIVE LOGITS

 least

0.45

least

0.37

 å½

0.33

_least

0.32

Least

0.30

ypical

0.30

kinson

0.29

OMIC

0.29

 Least

0.27

bÃ¶

0.27

Activations Density 0.009%

at

No Comments

No Known Activations