INDEX

Explanations

peptide

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

æ»ĭåĳ³

-0.27

 Oscars

-0.26

åĵģ

-0.26

å±Ĭ

-0.25

-road

-0.25

gew

-0.24

.scope

-0.24

æ¶µ

-0.24

tÃ³n

-0.24

 HOLDERS

-0.24

POSITIVE LOGITS

egade

0.28

è¾ĵ

0.27

.ide

0.27

gaard

0.27

ä¸Ģé¡¹

0.26

early

0.25

ustr

0.25

.XPath

0.25

 tiá»ģn

0.24

 early

0.24

Activations Density 0.016%

peptide

No Comments

No Known Activations