INDEX

Explanations

numbers and math

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

-Un

-0.29

çŁŃçº¿

-0.27

çĬ¹

-0.27

å¤Ħäºİ

-0.26

çĮ¶

-0.25

lyn

-0.25

 poorly

-0.25

ujÄħc

-0.25

alan

-0.24

 unreachable

-0.24

POSITIVE LOGITS

 Vand

0.26

orks

0.26

IDAD

0.25

 shuffled

0.25

ivr

0.25

é¡¶

0.25

airs

0.24

æİ¨èĸ¦

0.24

 Peterson

0.24

idl

0.24

Activations Density 0.007%

numbers and math

No Comments

No Known Activations