INDEX

Explanations

code snippets

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

 Clyde

-0.29

åĬĽè¿ĺæĺ¯

-0.28

èĬ

-0.26

allas

-0.26

arel

-0.25

å¾Ĺç½ª

-0.25

ä¼ģä¸ļåıĳå±ķ

-0.24

ÑĭÐ²Ð°ÐµÑĤÑģÑı

-0.24

 Recover

-0.24

æĸ¥

-0.24

POSITIVE LOGITS

pedia

0.33

dy

0.25

 populated

0.25

PageIndex

0.25

ange

0.24

 parsers

0.24

PosX

0.24

 pret

0.24

_PS

0.24

æĻļé¤Ĳ

0.24

Activations Density 0.098%

code snippets

No Comments

No Known Activations