INDEX

Explanations

selling

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

itan

-0.31

TA

-0.28

dep

-0.26

LING

-0.26

him

-0.26

æĽ¦

-0.26

ATM

-0.25

ling

-0.25

BuildContext

-0.24

æĭ¼éŁ³

-0.24

POSITIVE LOGITS

çĽĬ

0.28

 Jays

0.27

 wohl

0.27

åħ¨æĺİæĺŁ

0.26

 maÃ§

0.25

èĳ«

0.25

gles

0.25

jr

0.25

çļĦåį±å®³

0.24

çļĦäººéĥ½

0.24

Activations Density 0.018%

selling

No Comments

No Known Activations