INDEX

Explanations

citations

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

 partial

-0.28

igest

-0.27

partial

-0.26

Partial

-0.26

 dial

-0.25

iss

-0.25

bal

-0.25

eder

-0.25

IV

-0.25

iew

-0.25

POSITIVE LOGITS

jours

0.28

izu

0.27

 washington

0.27

DSA

0.26

 ashes

0.26

éļĲèĶ½

0.26

æ²¿

0.26

hin

0.26

edList

0.25

dna

0.25

Activations Density 0.115%

citations

No Comments

No Known Activations