INDEX

Explanations

mere

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

gear

-0.27

å¤ļäºº

-0.27

Singleton

-0.26

singleton

-0.26

æĬķèµĦäºº

-0.26

wide

-0.25

åľ¨ç¾İåĽ½

-0.25

å¥

-0.25

 nobody

-0.25

scl

-0.25

POSITIVE LOGITS

 spatial

0.27

æĶ¯çº¿

0.26

 Spatial

0.26

 Thunder

0.26

assin

0.25

Spatial

0.25

 GetMessage

0.24

æŁ¥

0.24

æ°Ķæģ¯

0.24

:_

0.24

Activations Density 5.007%

mere

No Comments

No Known Activations