INDEX

Explanations

sun

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

_HOOK

-0.25

|i

-0.24

\Extension

-0.24

Unt

-0.24

-twitter

-0.24

NSE

-0.24

Muon

-0.24

BOSE

-0.23

uÃŃ

-0.23

é«ĺéĢŁ

-0.23

POSITIVE LOGITS

 sort

0.26

 Distance

0.26

ä¸ĭä¹¡

0.26

 Affero

0.26

ellas

0.25

 tá»ĩ

0.25

éĺ²æĻĴ

0.25

 summer

0.24

_TAB

0.24

 Sort

0.24

Activations Density 0.000%

sun

No Comments

No Known Activations