INDEX

Explanations

differences

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

vsp

-0.28

pper

-0.27

 hÃ´

-0.26

dap

-0.26

PPER

-0.26

utch

-0.25

abilia

-0.25

ãĥĪãĥĥãĥĹ

-0.25

æ°ĳéĸĵ

-0.25

çĶ±ä¸ŃåĽ½

-0.25

POSITIVE LOGITS

br

0.30

br

0.28

åĨ³

0.27

è®®æ¡Ī

0.27

fore

0.26

 algorithm

0.25

 forth

0.24

gorithm

0.24

æ»¡

0.24

åı«

0.24

Activations Density 0.034%

differences

No Comments

No Known Activations