INDEX

Explanations

Proper nouns 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

riba

-0.28

icits

-0.28

 indiv

-0.26

 twilight

-0.26

mounted

-0.25

 ConnectionState

-0.25

æ¶Īéĺ²å®īåħ¨

-0.25

 wood

-0.24

eve

-0.24

æĹ¥æĻļ

-0.24

POSITIVE LOGITS

ä¸Ģå®ļ

0.28

 altogether

0.26

sj

0.25

à¹ģ

0.25

esome

0.24

èĬ¡

0.24

akening

0.24

toJson

0.24

ighted

0.24

-review

0.24

Activations Density 1.113%

Proper nouns and locations

No Comments

No Known Activations