INDEX

Explanations

stop

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

 liners

-0.29

 probation

-0.27

.cycle

-0.26

bucks

-0.26

icate

-0.26

 Carm

-0.25

-block

-0.25

ç¯¦

-0.25

è¡Ģæ¶²å¾ªçİ¯

-0.24

igans

-0.24

POSITIVE LOGITS

jong

0.29

amb

0.27

èľļ

0.26

gob

0.26

æ¤įæłĳ

0.25

Nu

0.25

 conserv

0.25

viron

0.25

Nu

0.25

Roo

0.25

Activations Density 0.083%

stop

No Comments

No Known Activations