INDEX

Explanations

organizations and locations

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

 lids

-0.27

reffen

-0.27

 extr

-0.27

ãĥŃãĥ¼

-0.26

antor

-0.26

 pitches

-0.26

 squirt

-0.26

lice

-0.26

leys

-0.25

Ã¸j

-0.25

POSITIVE LOGITS

éķķ

0.27

æªĢ

0.26

heads

0.25

hausen

0.25

 Toll

0.25

çŁ¿çī©

0.25

 Governors

0.24

unr

0.24

WARE

0.24

sit

0.23

Activations Density 0.157%

organizations and locations

No Comments

No Known Activations