INDEX

Explanations

coding/programming

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

Xd

-0.27

è¿Ļè¾¹

-0.27

%%%

-0.26

éĥ½ä¼ļæľī

-0.26

_here

-0.26

è¿ĻéĩĮæľī

-0.25

ror

-0.25

ç§»åĪ°

-0.25

çĽ´åĪ°

-0.25

 Testament

-0.25

POSITIVE LOGITS

åħ¶å®ĥéĹ®é¢ĺ

0.26

æķħå®«

0.26

[src

0.25

Tri

0.25

.",

0.25

tempt

0.25

èĢģåħ¬

0.25

rel

0.25

é¢¦

0.24

erval

0.24

Activations Density 0.000%

coding/programming

No Comments

No Known Activations