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

æ¯ıä¸ªäººéĥ½

-0.27

çĽ®ãģ«

-0.26

åİ»çľĭçľĭ

-0.25

âĢ¦”

-0.25

 cult

-0.24

[âĢ¦

-0.24

Ļ¶

-0.23

arts

-0.23

(cd

-0.23

ÐµÑĢÐ¶

-0.23

POSITIVE LOGITS

Hur

0.27

å¤§å¤§å°ı

0.27

Hur

0.26

esses

0.26

ORN

0.25

ä¿İ

0.25

å£°éģĵ

0.25

lys

0.25

 trails

0.25

 whites

0.24

Activations Density 0.005%

code snippets

No Comments

No Known Activations